Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 20115
    Prev
    Next
    INDEX
    Explanations

    words related to authenticity or sincerity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "truly" indicating emphasis or sincerity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheong
    -0.76
     Procedures
    -0.75
     Picks
    -0.74
     Signs
    -0.67
     Pages
    -0.67
     Vehicles
    -0.65
     newsletters
    -0.65
     Landing
    -0.64
     Pieces
    -0.64
     screenings
    -0.64
    POSITIVE LOGITS
     appreciated
    0.82
     qualified
    0.76
    overe
    0.74
     motivated
    0.74
     fulfilled
    0.73
     honoured
    0.73
     appreciate
    0.72
     accomplished
    0.71
    initions
    0.71
     cared
    0.70
    Activations Density 0.010%

    No Known Activations